Menu

Dynamic Algorithm Configuration and Optimization

You can register for the seminar via HISinOne.

Background

Hyperparameter optimization is a powerful approach to achieve the best performance on many different problems. However, automated approaches to solve this problem tend to ignore the iterative nature of many algorithms. With the dynamic algorithm configuration (DAC) framework we can generalize over prior optimization approaches, as well as handle optimization of hyperparameters that need to be adjusted over multiple time-steps. In this seminar, we will discuss applications (such as temporally extended epsilon greedy exploration in RL) and domains (e.g., reinforcement learning, evolutionary algorithms or deep learning) that can benefit from dynamic configuration methods. A large portion of the seminar will be dedicated to discussing papers that describe DAC methods that employ reinforcement learning to learn hyperparameter optimization policies for various domains.

Requirements

We require that you have taken lectures on

  • Machine Learning, and/or
  • Deep Learning

We strongly recommend that you have heard lectures on

  • Automated Machine Learning
  • Reinforcement Learning

Organization

Every week all students read the relevant literature. Two studens will prepare presentations for the topics of the week and present it in the session. After each presentation, we will have time for a question & discussion round and all participants are expected to take part in these. At the end of the semester, each student has to write a short paper about their assigned topic.

Note: We are currently evaluating if we will offer the seminar purely as in-person format or if we will do a hybrid setup.

Grading

  • Presentation: 40%
  • Paper: 40%
  • Participation in Discussions: 20%

Schedule

Date
(14:00-16:00)
TopicMain LiteratureAdditional Literature
18.10.2022Introduction of the topic and the available literature--
25.10.2022How to give a good presentation & How to write a report--
01.11.2022No meeting due to a public holiday--
08.11.2022
15.11.2022
22.11.2022
29.11.2022
06.12.2022
13.12.2022
20.12.2022
27.12.2022Christmas Break--
03.01.2023Christmas Break--
10.01.2023
17.01.2023
24.01.2023
31.01.2023
07.02.2023

Literature

Relevant literature can be found at https://www.automl.org/automated-algorithm-design/dac/literature-overview. This list contains many, though not all of the papers that we intend to cover in the seminar.